Modular Differential Evolution

TL;DR

This paper introduces a modular framework for Differential Evolution, enabling fair comparison and detailed exploration of algorithm variants, leading to improved tuning and understanding of DE performance.

Contribution

It proposes a modular framework for DE that facilitates comparison, tuning, and analysis of different algorithmic variants within a unified structure.

Findings

Tuned modular DE significantly outperforms standard DE variants.

The modular approach allows detailed analysis of module effects on performance.

Tuning within the framework improves optimization results.

Abstract

New contributions in the field of iterative optimisation heuristics are often made in an iterative manner. Novel algorithmic ideas are not proposed in isolation, but usually as an extension of a preexisting algorithm. Although these contributions are often compared to the base algorithm, it is challenging to make fair comparisons between larger sets of algorithm variants. This happens because even small changes in the experimental setup, parameter settings, or implementation details can cause results to become incomparable. Modular algorithms offer a way to overcome these challenges. By implementing the algorithmic modifications into a common framework, many algorithm variants can be compared, while ensuring that implementation details match in all versions. In this work, we propose a version of a modular framework for the popular Differential Evolution (DE) algorithm. We show that this modular approach not only aids in comparison, but also allows for a much more detailed exploration of the space of possible DE variants. This is illustrated by showing that tuning the settings of modular DE vastly outperforms a set of commonly used DE versions which have been recreated in our framework. We then investigate these tuned algorithms in detail, highlighting the relation between modules and performance on particular problems.